@inproceedings{dutta-etal-2026-auditing,
    title = "Auditing {LLM} Responses to Harmful Stereotypes Targeting Mental Health Groups",
    author = "Dutta, Arka  and
      Magu, Rijul  and
      Kim, Sean  and
      Yoon, Seohee  and
      De Choudhury, Munmun  and
      KhudaBukhsh, Ashiqur R.",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.2010/",
    pages = "40435--40452",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) can exhibit imbalanced biases against vulnerable groups, but how they rationalize stereotypes and rights restrictions targeting mental health entities remains underexplored. We audit a broad suite of open-weight LLMs on stereotype-justification prompts tied to mental health identities. We find that several widely used models endorse harmful stereotypes when explicitly asked to justify them, with endorsement varying across model families, versions, and mental health conditions. Finally, we show that widely used harmful-content evaluation and moderation frameworks often miss these nuanced, discriminatory responses, highlighting a gap in current AI safety evaluation for mental health groups."
}